English
Related papers

Related papers: Span-Agnostic Optimal Sample Complexity and Oracle…

200 papers

Dynamic optimization of mean and variance in Markov decision processes (MDPs) is a long-standing challenge caused by the failure of dynamic programming. In this paper, we propose a new approach to find the globally optimal policy for…

Optimization and Control · Mathematics 2023-02-28 Li Xia , Shuai Ma

It is well-known that given a smooth, bounded-from-below, and possibly nonconvex function, standard gradient-based methods can find $\epsilon$-stationary points (with gradient norm less than $\epsilon$) in $\mathcal{O}(1/\epsilon^2)$…

Optimization and Control · Mathematics 2022-10-28 Guy Kornowski , Ohad Shamir

We consider the problem of minimizing the number of matrix-vector queries needed for accurate trace estimation in the dynamic setting where our underlying matrix is changing slowly, such as during an optimization process. Specifically, for…

Data Structures and Algorithms · Computer Science 2022-10-03 David P. Woodruff , Fred Zhang , Qiuyi Zhang

There have been many recent advances on provably efficient Reinforcement Learning (RL) in problems with rich observation spaces. However, all these works share a strong realizability assumption about the optimal value function of the true…

Machine Learning · Computer Science 2021-06-23 Christoph Dann , Yishay Mansour , Mehryar Mohri , Ayush Sekhari , Karthik Sridharan

A central issue lying at the heart of online reinforcement learning (RL) is data efficiency. While a number of recent works achieved asymptotically minimal regret in online RL, the optimality of these results is only guaranteed in a…

Machine Learning · Computer Science 2025-04-30 Zihan Zhang , Yuxin Chen , Jason D. Lee , Simon S. Du

We study the problem of infinite-horizon average-reward reinforcement learning with linear Markov decision processes (MDPs). The associated Bellman operator of the problem not being a contraction makes the algorithm design challenging.…

Machine Learning · Statistics 2025-03-12 Kihyuk Hong , Woojin Chae , Yufan Zhang , Dabeen Lee , Ambuj Tewari

We investigate the sample complexity of learning the optimal arm for multi-task bandit problems. Arms consist of two components: one that is shared across tasks (that we call representation) and one that is task-specific (that we call…

Machine Learning · Statistics 2022-11-29 Alessio Russo , Alexandre Proutiere

Designing sample-efficient and computationally feasible reinforcement learning (RL) algorithms is particularly challenging in environments with large or infinite state and action spaces. In this paper, we advance this effort by presenting…

Machine Learning · Computer Science 2024-10-04 Zakaria Mhammedi

Dealing with Partially Observable Markov Decision Processes is notably a challenging task. We face an average-reward infinite-horizon POMDP setting with an unknown transition model, where we assume the knowledge of the observation model.…

Machine Learning · Computer Science 2024-10-03 Alessio Russo , Alberto Maria Metelli , Marcello Restelli

We introduce a generic template for developing regret minimization algorithms in the Stochastic Shortest Path (SSP) model, which achieves minimax optimal regret as long as certain properties are ensured. The key of our analysis is a new…

Machine Learning · Computer Science 2021-11-11 Liyu Chen , Mehdi Jafarnia-Jahromi , Rahul Jain , Haipeng Luo

In probably approximately correct (PAC) reinforcement learning (RL), an agent is required to identify an $\epsilon$-optimal policy with probability $1-\delta$. While minimax optimal algorithms exist for this problem, its instance-dependent…

Machine Learning · Computer Science 2022-10-25 Andrea Tirinzoni , Aymen Al-Marjani , Emilie Kaufmann

We consider a regularized expected reward optimization problem in the non-oblivious setting that covers many existing problems in reinforcement learning (RL). In order to solve such an optimization problem, we apply and analyze the…

Machine Learning · Computer Science 2024-08-21 Ling Liang , Haizhao Yang

Penalty methods are a well known class of algorithms for constrained optimization. They transform a constrained problem into a sequence of unconstrained \emph{penalized} problems in the hope that approximate solutions of the latter converge…

Optimization and Control · Mathematics 2025-12-01 Youssef Diouane , Maxence Gollier , Dominique Orban

We present a unified framework based on primal-dual stochastic mirror descent for approximately solving infinite-horizon Markov decision processes (MDPs) given a generative model. When applied to an average-reward MDP with $A_{tot}$ total…

Machine Learning · Computer Science 2020-08-31 Yujia Jin , Aaron Sidford

We introduce a new approach to develop stochastic optimization algorithms for a class of stochastic composite and possibly nonconvex optimization problems. The main idea is to combine two stochastic estimators to create a new hybrid one. We…

Optimization and Control · Mathematics 2020-05-05 Quoc Tran-Dinh , Nhan H. Pham , Dzung T. Phan , Lam M. Nguyen

We consider the problem of solving robust Markov decision process (MDP), which involves a set of discounted, finite state, finite action space MDPs with uncertain transition kernels. The goal of planning is to find a robust policy that…

Machine Learning · Computer Science 2023-06-13 Yan Li , Guanghui Lan , Tuo Zhao

One of the key approaches to save samples in reinforcement learning (RL) is to use knowledge from an approximate model such as its simulator. However, how much does an approximate model help to learn a near-optimal policy of the true…

Machine Learning · Computer Science 2020-07-15 Fei Feng , Wotao Yin , Lin F. Yang

We study the problem of estimating the one-point specification probabilities in non-necessary finite discrete random fields from partially observed independent samples. Our procedures are based on model selection by minimization of a…

Statistics Theory · Mathematics 2016-01-18 Matthieu Lerasle , Daniel Y. Takahashi

Multi-distribution learning (MDL), which seeks to learn a shared model that minimizes the worst-case risk across $k$ distinct data distributions, has emerged as a unified framework in response to the evolving demand for robustness,…

Machine Learning · Computer Science 2025-08-12 Zihan Zhang , Wenhao Zhan , Yuxin Chen , Simon S. Du , Jason D. Lee

We study the sequential decision making problem of maximizing the expected total reward while satisfying a constraint on the expected total utility. We employ the natural policy gradient method to solve the discounted infinite-horizon…

Optimization and Control · Mathematics 2025-10-16 Dongsheng Ding , Kaiqing Zhang , Jiali Duan , Tamer Başar , Mihailo R. Jovanović
‹ Prev 1 4 5 6 7 8 10 Next ›